PyTorchKR Papers

최신 논문

총 6,233편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2404.15954

Mixed Supervised Graph Contrastive Learning for Recommendation

Recommender systems (RecSys) play a vital role in online platforms, offering users personalized suggestions amidst vast information. Graph contrastive learning aims to learn from high-order collaborative filtering signals with unsupervised augmentation on the user-item bipartite graph, which predominantly relies on the multi-task learning framework involving both the pair-wise recommendation loss and the contrastive loss. This decoupled design can cause inconsistent optimization direction from different losses, which leads to longer convergence time and even sub-optimal performance. Besides, the self-supervised contrastive loss falls short in alleviating the data sparsity issue in RecSys as it learns to differentiate users/items from different views without providing extra supervised collaborative filtering signals during augmentations. In this paper, we propose Mixed Supervised Graph Contrastive Learning for Recommendation (MixSGCL) to address these concerns. MixSGCL originally integrates the training of recommendation and unsupervised contrastive losses into a supervised contrastive learning loss to align the two tasks within one optimization direction. To cope with the data sparsity issue, instead unsupervised augmentation, we further propose node-wise and edge-wise mixup to mine more direct supervised collaborative filtering signals based on existing user-item interactions. Extensive experiments on three real-world datasets demonstrate that MixSGCL surpasses state-of-the-art methods, achieving top performance on both accuracy and efficiency. It validates the effectiveness of MixSGCL with our coupled design on supervised graph contrastive learning.

arXiv:2404.15854공식 코드 · Papers with Code

CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning

The increasing prevalence of audio deepfakes poses significant security threats, necessitating robust detection methods. While existing detection systems exhibit promise, their robustness against malicious audio manipulations remains underexplored. To bridge the gap, we undertake the first comprehensive study of the susceptibility of the most widely adopted audio deepfake detectors to manipulation attacks. Surprisingly, even manipulations like volume control can significantly bypass detection without affecting human perception. To address this, we propose CLAD (Contrastive Learning-based Audio deepfake Detector) to enhance the robustness against manipulation attacks. The key idea is to incorporate contrastive learning to minimize the variations introduced by manipulations, therefore enhancing detection robustness. Additionally, we incorporate a length loss, aiming to improve the detection accuracy by clustering real audios more closely in the feature space. We comprehensively evaluated the most widely adopted audio deepfake detection models and our proposed CLAD against various manipulation attacks. The detection models exhibited vulnerabilities, with FAR rising to 36.69%, 31.23%, and 51.28% under volume control, fading, and noise injection, respectively. CLAD enhanced robustness, reducing the FAR to 0.81% under noise injection and consistently maintaining an FAR below 1.63% across all tests. Our source code and documentation are available in the artifact repository (https://github.com/CLAD23/CLAD).

arXiv:2404.16773

ConKeD++ -- Improving descriptor learning for retinal image registration: A comprehensive study of contrastive losses

Self-supervised contrastive learning has emerged as one of the most successful deep learning paradigms. In this regard, it has seen extensive use in image registration and, more recently, in the particular field of medical image registration. In this work, we propose to test and extend and improve a state-of-the-art framework for color fundus image registration, ConKeD. Using the ConKeD framework we test multiple loss functions, adapting them to the framework and the application domain. Furthermore, we evaluate our models using the standarized benchmark dataset FIRE as well as several datasets that have never been used before for color fundus registration, for which we are releasing the pairing data as well as a standardized evaluation approach. Our work demonstrates state-of-the-art performance across all datasets and metrics demonstrating several advantages over current SOTA color fundus registration methods

arXiv:2404.16416

Learning Discriminative Spatio-temporal Representations for Semi-supervised Action Recognition

Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to making ambiguous predictions under scarce labeled data, embodied as the limitation of distinguishing different actions with similar spatio-temporal information. In this paper, we approach this problem by empowering the model two aspects of capability, namely discriminative spatial modeling and temporal structure modeling for learning discriminative spatio-temporal representations. Specifically, we propose an Adaptive Contrastive Learning~(ACL) strategy. It assesses the confidence of all unlabeled samples by the class prototypes of the labeled data, and adaptively selects positive-negative samples from a pseudo-labeled sample bank to construct contrastive learning. Additionally, we introduce a Multi-scale Temporal Learning~(MTL) strategy. It could highlight informative semantics from long-term clips and integrate them into the short-term clip while suppressing noisy information. Afterwards, both of these two new techniques are integrated in a unified framework to encourage the model to make accurate predictions. Extensive experiments on UCF101, HMDB51 and Kinetics400 show the superiority of our method over prior state-of-the-art approaches.

arXiv:2404.16336공식 코드 · Papers with Code

FedStyle: Style-Based Federated Learning Crowdsourcing Framework for Art Commissions

The unique artistic style is crucial to artists' occupational competitiveness, yet prevailing Art Commission Platforms rarely support style-based retrieval. Meanwhile, the fast-growing generative AI techniques aggravate artists' concerns about releasing personal artworks to public platforms. To achieve artistic style-based retrieval without exposing personal artworks, we propose FedStyle, a style-based federated learning crowdsourcing framework. It allows artists to train local style models and share model parameters rather than artworks for collaboration. However, most artists possess a unique artistic style, resulting in severe model drift among them. FedStyle addresses such extreme data heterogeneity by having artists learn their abstract style representations and align with the server, rather than merely aggregating model parameters lacking semantics. Besides, we introduce contrastive learning to meticulously construct the style representation space, pulling artworks with similar styles closer and keeping different ones apart in the embedding space. Extensive experiments on the proposed datasets demonstrate the superiority of FedStyle.

arXiv:2404.15653공식 코드 · Papers with Code

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data

Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise similarity computation in contrastive loss between image and text pairs poses computational challenges. This paper presents a novel weakly supervised pre-training of vision models on web-scale image-text data. The proposed method reframes pre-training on image-text data as a classification task. Consequently, it eliminates the need for pairwise similarity computations in contrastive loss, achieving a remarkable $2.7\times$ acceleration in training speed compared to contrastive learning on web-scale data. Through extensive experiments spanning diverse vision tasks, including detection and segmentation, we demonstrate that the proposed method maintains high representation quality. Our source code along with pre-trained model weights and training recipes is available at \url{https://github.com/apple/corenet}.

arXiv:2404.16532공식 코드 · Papers with Code

Global Concept Explanations for Graphs by Contrastive Learning

Beyond improving trust and validating model fairness, xAI practices also have the potential to recover valuable scientific insights in application domains where little to no prior human intuition exists. To that end, we propose a method to extract global concept explanations from the predictions of graph neural networks to develop a deeper understanding of the tasks underlying structure-property relationships. We identify concept explanations as dense clusters in the self-explaining Megan models subgraph latent space. For each concept, we optimize a representative prototype graph and optionally use GPT-4 to provide hypotheses about why each structure has a certain effect on the prediction. We conduct computational experiments on synthetic and real-world graph property prediction tasks. For the synthetic tasks we find that our method correctly reproduces the structural rules by which they were created. For real-world molecular property regression and classification tasks, we find that our method rediscovers established rules of thumb. More specifically, our results for molecular mutagenicity prediction indicate more fine-grained resolution of structural details than existing explainability methods, consistent with previous results from chemistry literature. Overall, our results show promising capability to extract the underlying structure-property relationships for complex graph property prediction tasks.

논문 ID: document/1041581

Hypergraph Contrastive Learning for Drug Trafficking Community Detection

In recent decades, due to the lucrative profits, the crime of drug trafficking has evolved with modern technologies. Social media, as one of the popular online platforms, have become direct-to-consumer intermediaries for illicit drug trafficking communities to promote and trade drugs. These group-wise drug trafficking activities pose significant challenges to public health and safety, requiring urgent measures to address this issue. However, existing works against the imminent problem still face limitations, such as primarily analyzing individual roles from a single perspective, ignoring the group-wise relationships, and requiring sufficient labeled samples for model training. To this end, we propose a novel HyperGraph Contrastive Learning framework called HyGCL-DC that employs hypergraph to model the higher-order relationships among users to detect Drug trafficking Communities. Firstly, we build a hypergraph called Twitter-HyDrug including online user nodes and four types of hyperedges to depict the rich group-wise relationships among these users. Then, we leverage hypergraph neural networks to model the rich relationships among nodes and hyperedges in the drug trafficking hypergraph. Furthermore, we design a hypergraph self-supervised contrast module, which integrates the augmentation from the structure view and the attribute view to enhance hypergraph representation learning over unlabeled data. Finally, we design an end-to-end framework that combines the self-supervised contrastive module and the supervised module to classify online drug trafficking communities. To comprehensively study the online drug trafficking problem and evaluate our model, we conduct extensive experiments over Twitter-HyDrug and three citation benchmark hypergraph datasets to demonstrate the effectiveness of our model. Our new data and source code are available at https://github.com/GraphResearcher/HyGCL-DC.

arXiv:2404.14831공식 코드 · Papers with Code

Towards Universal Dense Blocking for Entity Resolution

Blocking is a critical step in entity resolution, and the emergence of neural network-based representation models has led to the development of dense blocking as a promising approach for exploring deep semantics in blocking. However, previous advanced self-supervised dense blocking approaches require domain-specific training on the target domain, which limits the benefits and rapid adaptation of these methods. To address this issue, we propose UniBlocker, a dense blocker that is pre-trained on a domain-independent, easily-obtainable tabular corpus using self-supervised contrastive learning. By conducting domain-independent pre-training, UniBlocker can be adapted to various downstream blocking scenarios without requiring domain-specific fine-tuning. To evaluate the universality of our entity blocker, we also construct a new benchmark covering a wide range of blocking tasks from multiple domains and scenarios. Our experiments show that the proposed UniBlocker, without any domain-specific learning, significantly outperforms previous self- and unsupervised dense blocking methods and is comparable and complementary to the state-of-the-art sparse blocking methods.

arXiv:2404.15272

CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios

Medical Vision-Language Pretraining (Med-VLP) establishes a connection between visual content from medical images and the relevant textual descriptions. Existing Med-VLP methods primarily focus on 2D images depicting a single body part, notably chest X-rays. In this paper, we extend the scope of Med-VLP to encompass 3D images, specifically targeting full-body scenarios, by using a multimodal dataset of CT images and reports. Compared with the 2D counterpart, 3D VLP is required to effectively capture essential semantics from significantly sparser representation in 3D imaging. In this paper, we introduce CT-GLIP (Grounded Language-Image Pretraining with CT scans), a novel method that constructs organ-level image-text pairs to enhance multimodal contrastive learning, aligning grounded visual features with precise diagnostic text. Additionally, we developed an abnormality dictionary to augment contrastive learning with diverse contrastive pairs. Our method, trained on a multimodal CT dataset comprising 44,011 organ-level vision-text pairs from 17,702 patients across 104 organs, demonstrates it can identify organs and abnormalities in a zero-shot manner using natural languages. The performance of CT-GLIP is validated on a separate test set of 1,130 patients, focusing on the 16 most frequent abnormalities across 7 organs. The experimental results show our model's superior performance over the standard CLIP framework across zero-shot and fine-tuning scenarios, using both CNN and ViT architectures.

arXiv:2404.13905

SI-FID: Only One Objective Indicator for Evaluating Stitched Images

Image quality evaluation accurately is vital in developing image stitching algorithms as it directly reflects the algorithms progress. However, commonly used objective indicators always produce inconsistent and even conflicting results with subjective indicators. To enhance the consistency between objective and subjective evaluations, this paper introduces a novel indicator the Frechet Distance for Stitched Images (SI-FID). To be specific, our training network employs the contrastive learning architecture overall. We employ data augmentation approaches that serve as noise to distort images in the training set. Both the initial and distorted training sets are then input into the pre-training model for fine-tuning. We then evaluate the altered FID after introducing interference to the test set and examine if the noise can improve the consistency between objective and subjective evaluation results. The rank correlation coefficient is utilized to measure the consistency. SI-FID is an altered FID that generates the highest rank correlation coefficient under the effect of a certain noise. The experimental results demonstrate that the rank correlation coefficient obtained by SI-FID is at least 25% higher than other objective indicators, which means achieving evaluation results closer to human subjective evaluation.

arXiv:2404.13878공식 코드 · Papers with Code

Multi-Level Sequence Denoising with Cross-Signal Contrastive Learning for Sequential Recommendation

Sequential recommender systems (SRSs) aim to suggest next item for a user based on her historical interaction sequences. Recently, many research efforts have been devoted to attenuate the influence of noisy items in sequences by either assigning them with lower attention weights or discarding them directly. The major limitation of these methods is that the former would still prone to overfit noisy items while the latter may overlook informative items. To the end, in this paper, we propose a novel model named Multi-level Sequence Denoising with Cross-signal Contrastive Learning (MSDCCL) for sequential recommendation. To be specific, we first introduce a target-aware user interest extractor to simultaneously capture users' long and short term interest with the guidance of target items. Then, we develop a multi-level sequence denoising module to alleviate the impact of noisy items by employing both soft and hard signal denoising strategies. Additionally, we extend existing curriculum learning by simulating the learning pattern of human beings. It is worth noting that our proposed model can be seamlessly integrated with a majority of existing recommendation models and significantly boost their effectiveness. Experimental studies on five public datasets are conducted and the results demonstrate that the proposed MSDCCL is superior to the state-of-the-art baselines. The source code is publicly available at https://github.com/lalunex/MSDCCL/tree/main.

arXiv:2404.13556공식 코드 · Papers with Code

ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval

Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent complex conversational sessions for dense retrieval. To achieve this, we propose a simple and effective dual-learning approach that adapts LLM for retrieval via contrastive learning while enhancing the complex session understanding through masked instruction tuning on high-quality conversational instruction tuning data. Extensive experiments on five conversational search benchmarks demonstrate that ChatRetriever substantially outperforms existing conversational dense retrievers, achieving state-of-the-art performance on par with LLM-based rewriting approaches. Furthermore, ChatRetriever exhibits superior robustness in handling diverse conversational contexts. Our work highlights the potential of adapting LLMs for retrieval with complex inputs like conversational search sessions and proposes an effective approach to advance this research direction.

arXiv:2404.13631

Fermi-Bose Machine achieves both generalization and adversarial robustness

Distinct from human cognitive processing, deep neural networks trained by backpropagation can be easily fooled by adversarial examples. To design a semantically meaningful representation learning, we discard backpropagation, and instead, propose a local contrastive learning, where the representation for the inputs bearing the same label shrink (akin to boson) in hidden layers, while those of different labels repel (akin to fermion). This layer-wise learning is local in nature, being biological plausible. A statistical mechanics analysis shows that the target fermion-pair-distance is a key parameter. Moreover, the application of this local contrastive learning to MNIST benchmark dataset demonstrates that the adversarial vulnerability of standard perceptron can be greatly mitigated by tuning the target distance, i.e., controlling the geometric separation of prototype manifolds.

arXiv:2404.13324

Collaborative Visual Place Recognition through Federated Learning

Visual Place Recognition (VPR) aims to estimate the location of an image by treating it as a retrieval problem. VPR uses a database of geo-tagged images and leverages deep neural networks to extract a global representation, called descriptor, from each image. While the training data for VPR models often originates from diverse, geographically scattered sources (geo-tagged images), the training process itself is typically assumed to be centralized. This research revisits the task of VPR through the lens of Federated Learning (FL), addressing several key challenges associated with this adaptation. VPR data inherently lacks well-defined classes, and models are typically trained using contrastive learning, which necessitates a data mining step on a centralized database. Additionally, client devices in federated systems can be highly heterogeneous in terms of their processing capabilities. The proposed FedVPR framework not only presents a novel approach for VPR but also introduces a new, challenging, and realistic task for FL research, paving the way to other image retrieval tasks in FL.

arXiv:2404.14109공식 코드 · Papers with Code

CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective

In this paper, we present a simple yet effective contrastive knowledge distillation approach, which can be formulated as a sample-wise alignment problem with intra- and inter-sample constraints. Unlike traditional knowledge distillation methods that concentrate on maximizing feature similarities or preserving class-wise semantic correlations between teacher and student features, our method attempts to recover the "dark knowledge" by aligning sample-wise teacher and student logits. Specifically, our method first minimizes logit differences within the same sample by considering their numerical values, thus preserving intra-sample similarities. Next, we bridge semantic disparities by leveraging dissimilarities across different samples. Note that constraints on intra-sample similarities and inter-sample dissimilarities can be efficiently and effectively reformulated into a contrastive learning framework with newly designed positive and negative pairs. The positive pair consists of the teacher's and student's logits derived from an identical sample, while the negative pairs are formed by using logits from different samples. With this formulation, our method benefits from the simplicity and efficiency of contrastive learning through the optimization of InfoNCE, yielding a run-time complexity that is far less than $O(n^2)$, where $n$ represents the total number of training samples. Furthermore, our method can eliminate the need for hyperparameter tuning, particularly related to temperature parameters and large batch sizes. We conduct comprehensive experiments on three datasets including CIFAR-100, ImageNet-1K, and MS COCO. Experimental results clearly confirm the effectiveness of the proposed method on both image classification and object detection tasks. Our source codes will be publicly available at https://github.com/wencheng-zhu/CKD.

arXiv:2404.13711공식 코드 · Papers with Code

ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face Synthesis

Recent advances in generative visual models and neural radiance fields have greatly boosted 3D-aware image synthesis and stylization tasks. However, previous NeRF-based work is limited to single scene stylization, training a model to generate 3D-aware cartoon faces with arbitrary styles remains unsolved. We propose ArtNeRF, a novel face stylization framework derived from 3D-aware GAN to tackle this problem. In this framework, we utilize an expressive generator to synthesize stylized faces and a triple-branch discriminator module to improve the visual quality and style consistency of the generated faces. Specifically, a style encoder based on contrastive learning is leveraged to extract robust low-dimensional embeddings of style images, empowering the generator with the knowledge of various styles. To smooth the training process of cross-domain transfer learning, we propose an adaptive style blending module which helps inject style information and allows users to freely tune the level of stylization. We further introduce a neural rendering module to achieve efficient real-time rendering of images with higher resolutions. Extensive experiments demonstrate that ArtNeRF is versatile in generating high-quality 3D-aware cartoon faces with arbitrary styles.

arXiv:2404.13611

Video sentence grounding with temporally global textual knowledge

Temporal sentence grounding involves the retrieval of a video moment with a natural language query. Many existing works directly incorporate the given video and temporally localized query for temporal grounding, overlooking the inherent domain gap between different modalities. In this paper, we utilize pseudo-query features containing extensive temporally global textual knowledge sourced from the same video-query pair, to enhance the bridging of domain gaps and attain a heightened level of similarity between multi-modal features. Specifically, we propose a Pseudo-query Intermediary Network (PIN) to achieve an improved alignment of visual and comprehensive pseudo-query features within the feature space through contrastive learning. Subsequently, we utilize learnable prompts to encapsulate the knowledge of pseudo-queries, propagating them into the textual encoder and multi-modal fusion module, further enhancing the feature alignment between visual and language for better temporal grounding. Extensive experiments conducted on the Charades-STA and ActivityNet-Captions datasets demonstrate the effectiveness of our method.

arXiv:2404.13584

Rethink Arbitrary Style Transfer with Transformer and Contrastive Learning

Arbitrary style transfer holds widespread attention in research and boasts numerous practical applications. The existing methods, which either employ cross-attention to incorporate deep style attributes into content attributes or use adaptive normalization to adjust content features, fail to generate high-quality stylized images. In this paper, we introduce an innovative technique to improve the quality of stylized images. Firstly, we propose Style Consistency Instance Normalization (SCIN), a method to refine the alignment between content and style features. In addition, we have developed an Instance-based Contrastive Learning (ICL) approach designed to understand the relationships among various styles, thereby enhancing the quality of the resulting stylized images. Recognizing that VGG networks are more adept at extracting classification features and need to be better suited for capturing style features, we have also introduced the Perception Encoder (PE) to capture style features. Extensive experiments demonstrate that our proposed method generates high-quality stylized images and effectively prevents artifacts compared with the existing state-of-the-art methods.

arXiv:2404.14381공식 코드 · Papers with Code

TAVGBench: Benchmarking Text to Audible-Video Generation

The Text to Audible-Video Generation (TAVG) task involves generating videos with accompanying audio based on text descriptions. Achieving this requires skillful alignment of both audio and video elements. To support research in this field, we have developed a comprehensive Text to Audible-Video Generation Benchmark (TAVGBench), which contains over 1.7 million clips with a total duration of 11.8 thousand hours. We propose an automatic annotation pipeline to ensure each audible video has detailed descriptions for both its audio and video contents. We also introduce the Audio-Visual Harmoni score (AVHScore) to provide a quantitative measure of the alignment between the generated audio and video modalities. Additionally, we present a baseline model for TAVG called TAVDiffusion, which uses a two-stream latent diffusion model to provide a fundamental starting point for further research in this area. We achieve the alignment of audio and video by employing cross-attention and contrastive learning. Through extensive experiments and evaluations on TAVGBench, we demonstrate the effectiveness of our proposed model under both conventional metrics and our proposed metrics.